SiNC+: Adaptive Camera-Based Vitals with Unsupervised Learning of Periodic Signals

• URL: http://arxiv.org/abs/2404.13449v1
• Date: Sat, 20 Apr 2024 19:17:40 GMT
• Title: SiNC+: Adaptive Camera-Based Vitals with Unsupervised Learning of Periodic Signals
• Authors: Jeremy Speth, Nathan Vance, Patrick Flynn, Adam Czajka,
• Abstract summary: We present the first non-contrastive unsupervised learning framework for signal regression. We find that encouraging sparse power spectra within normal physiological bandlimits and variance over batches of power spectra is sufficient for learning periodic signals.
• Score: 6.458510829614774
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Subtle periodic signals, such as blood volume pulse and respiration, can be extracted from RGB video, enabling noncontact health monitoring at low cost. Advancements in remote pulse estimation -- or remote photoplethysmography (rPPG) -- are currently driven by deep learning solutions. However, modern approaches are trained and evaluated on benchmark datasets with ground truth from contact-PPG sensors. We present the first non-contrastive unsupervised learning framework for signal regression to mitigate the need for labelled video data. With minimal assumptions of periodicity and finite bandwidth, our approach discovers the blood volume pulse directly from unlabelled videos. We find that encouraging sparse power spectra within normal physiological bandlimits and variance over batches of power spectra is sufficient for learning visual features of periodic signals. We perform the first experiments utilizing unlabelled video data not specifically created for rPPG to train robust pulse rate estimators. Given the limited inductive biases, we successfully applied the same approach to camera-based respiration by changing the bandlimits of the target signal. This shows that the approach is general enough for unsupervised learning of bandlimited quasi-periodic signals from different domains. Furthermore, we show that the framework is effective for finetuning models on unlabelled video from a single subject, allowing for personalized and adaptive signal regressors.

Related papers

• Unsupervised Denoising for Signal-Dependent and Row-Correlated Imaging Noise [54.0185721303932]
  We present the first fully unsupervised deep learning-based denoiser capable of handling imaging noise that is row-correlated. Our approach uses a Variational Autoencoder with a specially designed autoregressive decoder. Our method does not require a pre-trained noise model and can be trained from scratch using unpaired noisy data.
  arXiv  Detail & Related papers  (2023-10-11T20:48:20Z)
• Contrast-Phys+: Unsupervised and Weakly-supervised Video-based Remote Physiological Measurement via Spatiotemporal Contrast [22.742875409103164]
  We propose Contrast-Phys+, a method that can be trained in both unsupervised and unsupervised settings. We employ a 3DCNN model to generate multiple rtemporal signals and incorporate prior knowledge of r into a contrastive loss function. Contrast-Phys+ outperforms the state-of-the-art supervised methods, even when using partially available or misaligned GT signals.
  arXiv  Detail & Related papers  (2023-09-13T12:50:21Z)
• Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection [64.65563422852568]
  We improve the challenging monocular 3D object detection problem with a general semi-supervised framework. We introduce a novel, simple, yet effective Augment and Criticize' framework that explores abundant informative samples from unlabeled data. The two new detectors, dubbed 3DSeMo_DLE and 3DSeMo_FLEX, achieve state-of-the-art results with remarkable improvements for over 3.5% AP_3D/BEV (Easy) on KITTI.
  arXiv  Detail & Related papers  (2023-03-20T16:28:15Z)
• Non-Contrastive Unsupervised Learning of Physiological Signals from Video [4.8327232174895745]
  We present the first non-contrastive unsupervised learning framework for signal regression to break free from labelled video data. With minimal assumptions of periodicity and finite bandwidth, our approach is capable of discovering blood volume pulse directly from unlabelled videos.
  arXiv  Detail & Related papers  (2023-03-14T14:34:51Z)
• Facial Video-based Remote Physiological Measurement via Self-supervised Learning [9.99375728024877]
  We introduce a novel framework that learns to estimate r signals from facial videos without the need of ground truth signals. Negative samples are generated via a learnable frequency module, which performs nonlinear signal frequency transformation. Next, we introduce a local r expert aggregation module to estimate r signals from augmented samples. It encodes complementary pulsation information from different face regions and aggregate them into one r prediction.
  arXiv  Detail & Related papers  (2022-10-27T13:03:23Z)
• Monitoring MBE substrate deoxidation via RHEED image-sequence analysis by deep learning [62.997667081978825]
  We present an approach for automated surveillance of GaAs substrate deoxidation in MBE using deep learning based RHEED image-sequence classification. Our approach consists of an non-supervised auto-encoder (AE) for feature extraction, combined with a supervised convolutional network.
  arXiv  Detail & Related papers  (2022-10-07T10:01:06Z)
• Contrast-Phys: Unsupervised Video-based Remote Physiological Measurement via Spatiotemporal Contrast [17.691683039742323]
  Video-based remote physiological measurement face videos to measure the blood volume change signal, which is also called remote photoplethysmography (r) We use a 3DCNN model to generate multiple rtemporal signals from each video in different locations and train the model with a contrastive loss where r signals from the same video are pulled together while those from different videos are pushed away.
  arXiv  Detail & Related papers  (2022-08-08T19:30:57Z)
• Disentangled Representation Learning for RF Fingerprint Extraction under Unknown Channel Statistics [77.13542705329328]
  We propose a framework of disentangled representation learning(DRL) that first learns to factor the input signals into a device-relevant component and a device-irrelevant component via adversarial learning. The implicit data augmentation in the proposed framework imposes a regularization on the RFF extractor to avoid the possible overfitting of device-irrelevant channel statistics. Experiments validate that the proposed approach, referred to as DR-RFF, outperforms conventional methods in terms of generalizability to unknown complicated propagation environments.
  arXiv  Detail & Related papers  (2022-08-04T15:46:48Z)
• WPPG Net: A Non-contact Video Based Heart Rate Extraction Network Framework with Compatible Training Capability [21.33542693986985]
  Our facial skin presents subtle color change known as remote Photoplethys (r) signal, from which we could extract the heart rate of the subject. Recently many deep learning methods and related datasets on r signal extraction are proposed. However, because of the time consumption blood flowing through our body and other factors, label waves such as BVP signals have uncertain delays with real r signals in some datasets. In this paper, by analyzing the common characteristics on rhythm and periodicity of r signals and label waves, we propose a whole set of training methodology which wraps these networks so that they could remain efficient when be trained at
  arXiv  Detail & Related papers  (2022-07-04T19:52:30Z)
• PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer [55.936527926778695]
  Recent deep learning approaches focus on mining subtle r clues using convolutional neural networks with limited-temporal receptive fields. In this paper, we propose the PhysFormer, an end-to-end video transformer based architecture.
  arXiv  Detail & Related papers  (2021-11-23T18:57:11Z)
• Video-based Person Re-identification without Bells and Whistles [49.51670583977911]
  Video-based person re-identification (Re-ID) aims at matching the video tracklets with cropped video frames for identifying the pedestrians under different cameras. There exists severe spatial and temporal misalignment for those cropped tracklets due to the imperfect detection and tracking results generated with obsolete methods. We present a simple re-Detect and Link (DL) module which can effectively reduce those unexpected noise through applying the deep learning-based detection and tracking on the cropped tracklets.
  arXiv  Detail & Related papers  (2021-05-22T10:17:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.